{"id":15290500,"url":"https://github.com/cool-rr/marley","last_synced_at":"2025-04-05T05:03:39.569Z","repository":{"id":56157929,"uuid":"301722703","full_name":"cool-RR/marley","owner":"cool-RR","description":"A framework for multi-agent reinforcement learning.","archived":false,"fork":false,"pushed_at":"2022-05-21T12:17:52.000Z","size":32165,"stargazers_count":272,"open_issues_count":10,"forks_count":26,"subscribers_count":13,"default_branch":"master","last_synced_at":"2025-04-05T05:03:26.828Z","etag":null,"topics":["ai","hacktoberfest","keras","machine-learning","python","q-learning","reinforcement-learning","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cool-RR.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-10-06T12:41:44.000Z","updated_at":"2025-03-21T16:09:44.000Z","dependencies_parsed_at":"2022-08-15T13:50:25.089Z","dependency_job_id":null,"html_url":"https://github.com/cool-RR/marley","commit_stats":null,"previous_names":["cool-rr/grid_royale"],"tags_count":9,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cool-RR%2Fmarley","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cool-RR%2Fmarley/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cool-RR%2Fmarley/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cool-RR%2Fmarley/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cool-RR","download_url":"https://codeload.github.com/cool-RR/marley/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247289409,"owners_count":20914464,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","hacktoberfest","keras","machine-learning","python","q-learning","reinforcement-learning","tensorflow"],"created_at":"2024-09-30T16:08:25.033Z","updated_at":"2025-04-05T05:03:39.550Z","avatar_url":"https://github.com/cool-RR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Marley #\n\nMarley is a framework for multi-agent reinforcement learning. It lets you design a game and run experiments with multiple AI-powered agents playing that game.\n\n**Marley isn't ready for use yet; it works for my research purposes, but I haven't yet made the work needed to make it easy to understand for others.** If you're still interested in using it, feel free to read the code or [email me](mailto:ram@rachum.com) for help.\n\nI'm using Marley in my research mission to use machine learning to understand human society. I want to produce emergent reciprocation in selfish RL agents and use that to show social behavior. [Talk video](https://youtu.be/WMVqYYarFkQ), [slides](https://docs.google.com/presentation/d/1uBV2VkCfds_K3Aj7JimK1aE22AJSmLVoOg5oR4pOJU4/), [sign up for updates](https://groups.google.com/g/ram-rachum-research-announce).\n\nI hope to make Marley easier to use soon.\n\n## GridRoyale ##\n\n![](https://i.imgur.com/pmxEKnR.gif)\n\n## [View the live version here!](https://grid-royale.herokuapp.com/) ##\n\n**GridRoyale** is a life simulation. It's a case study that's bundled with Marley.\n\nGridRoyale is similar to [Game of Life](https://en.wikipedia.org/wiki/Conway%27s_Game_of_Life) or\n[GridWorld](https://towardsdatascience.com/reinforcement-learning-implement-grid-world-from-scratch-c5963765ebff),\nexcept I added game mechanics to encourage the players to behave socially. These game mechanics are\nsimilar to those in the [battle royale](https://en.wikipedia.org/wiki/Battle_royale_game) genre of\ncomputer games, which is why it's called GridRoyale.\n\nPlayers get 10 points for eating food, i.e. the dots that regenerate randomly. Players lose 5 points for colliding with other agents or walls. Players lose 10 points for being shot.\n\n\n# How to run GridRoyale #\n\nInstallation:\n\n```console\n$ pip install marley\n```\n\nRun the server:\n\n```console\n$ marley grid_royale demo\n```\n\nThis will automatically open a browser window and show you your simulation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcool-rr%2Fmarley","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcool-rr%2Fmarley","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcool-rr%2Fmarley/lists"}